Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1181 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1737. Min Range: -5.1737

Max Act: 5.1737. Min Act: -0.1700

Data Index: 732880 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 5.1737. Min Range: -5.1737

Max Act: 5.0799. Min Act: -0.1700

Data Index: 799266 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 5.1737. Min Range: -5.1737

Max Act: 5.0174. Min Act: -0.1700

Data Index: 1262641 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 5.1737. Min Range: -5.1737

Max Act: 5.0799. Min Act: -0.1700

Data Index: 629825 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 5.1737. Min Range: -5.1737

Max Act: 5.0487. Min Act: -0.1700

Data Index: 1218266 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.9862. Min Act: -0.1700

Data Index: 487885 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.9549. Min Act: -0.1700

Data Index: 292923 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.9237. Min Act: -0.1700

Data Index: 933404 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.9237. Min Act: -0.1700

Data Index: 331360 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8924. Min Act: -0.1700

Data Index: 771100 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8612. Min Act: -0.1700

Data Index: 617120 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8299. Min Act: -0.1700

Data Index: 548182 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8299. Min Act: -0.1700

Data Index: 906040 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8299. Min Act: -0.1700

Data Index: 463449 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8299. Min Act: -0.1700

Data Index: 1192876 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.7987. Min Act: -0.1700

Data Index: 239488 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.7674. Min Act: -0.1700

Data Index: 1179014 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8299. Min Act: -0.1700

Data Index: 1271396 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.8299. Min Act: -0.1700

Data Index: 434014 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 5.1737. Min Range: -5.1737

Max Act: 4.7987. Min Act: -0.1700

Data Index: 721222 (C4 (Web Text))

Max Activating Token Index: 752